Spiral gives your agent every tool with one account. Browse the tools →

Factory Droid · Audio

How to Use Whisper Large in Factory Droid

Whisper Large turns recorded speech into transcripts for interviews, lectures, and voice notes across many languages. It uses OpenAI's large-v2 model, so don't assume results match Whisper large-v3.

Prompts to try with Whisper Large in Factory Droid

Copy an example into Factory Droid, or ask in your own words.

Use Whisper Large to transcribe recordings/demo.wav in English. Compare the transcript with README.md and draft corrections to the documented behavior, citing timestamps.

Whisper LargeFactory Droid
Try asking
  • Use Whisper Large to transcribe recordings/planning.wav in English. Draft an issue list from explicit requests, then check the repository for work already completed.

  • Use Whisper Large to transcribe recordings/tutorial.wav in English. Use the returned word timings to draft an SRT caption file and flag passages that need audio review.

  • Use Whisper Large to transcribe recordings/interview.wav in French. Save the transcript separately from your English summary of the product feedback.

  • Use Whisper Large to transcribe recordings/benchmark.wav in English with numeral formatting enabled. Compare the spoken measurements with benchmarks/results.csv and report discrepancies without changing the data.

How to set up Whisper Large in Factory Droid

Pick the way that suits you. Each takes about two minutes.

Use Spiral's MCP server

  1. Add the server

    Droid saves it to your user config, ~/.factory/mcp.json, so it works in every project.

    droid mcp add spiral https://api.spiral.ai/mcp --type http
  2. Sign in

    Start droid, type /mcp, select spiral and authenticate it. Sign in to Spiral in the browser and click Authorize. No API key.

  3. Check it

    Spiral shows as connected. needs authentication means the sign-in did not finish: run /mcp again.

    droid mcp list

Use the Spiral skill

  1. Send Factory Droid this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. Install and sign in

    Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Whisper Large

    One request; the result comes back by polling or a webhook.

    curl https://api.spiral.ai/v1/runs \
      -H "Authorization: Bearer $SPIRAL_API_KEY" \
      -H "Content-Type: application/json" \
      -H "Idempotency-Key: $(uuidgen)" \
      -d '{
        "provider": "deepgram",
        "model": "whisper-large",
        "input": {
          "url": "<url>"
        }
      }'

Then paste one of the prompts above: Factory Droid finds Whisper Large on Spiral, shows the price and runs it.

Whisper Large providers and prices

Spiral runs Whisper Large through Deepgram. Open a card for today's price, with every fee included.

DeepgramAudio

Settings you can ask for

Whisper Large works from your URL. Ask Factory Droid for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Diarizeon or offoff

Deprecated: use diarize_model instead. Recognize speaker changes. Each word in the transcript will be assigned a speaker number starting at 0.

Encodinglinear16, flac, mulaw, amr-nb, amr-wb, opus, speex, or g729

Specify the expected encoding of your submitted audio

Languageaf, am, ar, as, az, ba, be, bg and 105 moreen

The BCP-47 language tag that hints at the primary spoken language.

Numeralson or offoff

Numerals converts numbers from written format to numerical format

Dictationon or offoff

Dictation mode for controlling formatting with dictated speech

Punctuateon or off

Add punctuation and capitalization to the transcript Left unset, smart_format adds punctuation; false turns it off even with smart_format.

Utt splita number0.8

Seconds to wait before detecting a pause between words in submitted audio

Paragraphson or offoff

Splits audio into paragraphs to improve transcript readability

Utteranceson or offoff

Segments speech into meaningful semantic units

Filler wordson or offoff

Filler Words can help transcribe interruptions in your audio, like "uh" and "um"

Measurementson or offoff

Spoken measurements will be converted to their corresponding abbreviations

Multichannelon or offoff

Transcribe each audio channel independently

Smart formaton or offoff

Apply formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability

Diarize modellatest, v1, or v2

Select and enable a specific diarization model version.

Detect entitieson or offoff

Identifies and extracts key entities from content in submitted audio

Profanity filteron or offoff

Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely

Every API field of Whisper Large Speech to Text is on its tool page: open its card above.

What can you do with Whisper Large in Factory Droid?

Turn recorded project discussions and narrated demos into text you can use alongside the code. Your agent can compare the transcript with project files and draft documentation or tasks for review.

Interview transcripts for reporting

Use Whisper Large to draft a transcript of a recorded interview. Review selected quotations against the audio before including them in an article.

Podcast editing notes

Transcribe podcast audio with Whisper Large, then ask your agent to identify passages worth editing or quoting. Keep timestamps beside each selection.

Lecture study materials

Turn a recorded lecture into text with Whisper Large, then have your agent organize the transcript into study notes and questions.

Multilingual research interviews

Use Whisper Large for French, German, Hindi, or Japanese interview recordings. Select the spoken language and arrange review by someone who understands it.

Voice notes for project work

Transcribe recorded ideas with Whisper Large, then ask your agent to turn the transcript into a task list. Check names and quantities before acting.

Draft captions for recorded lessons

Use Whisper Large transcripts and word timings as the starting point for captions. Have your agent arrange the text into readable cues for review.

Searchable audio archives

Transcribe recorded talks with Whisper Large, then have your agent index the text with links to the original recordings and timestamps.

Whisper Large success rate and speed on Spiral

Success and speed over the last 24 hours, across every run of these tools on Spiral.

Success rate
100.0%
Fastest median run time
7.4s
Runs, last 24 hours
28
ToolSuccessMedian timeRuns
Whisper Large Speech to Text100.0%7.4s28

Questions about Whisper Large in Factory Droid

Can Factory Droid use Whisper Large?

Yes. Add Spiral to Factory Droid as an MCP server, and Factory Droid can find and run Whisper Large like any built-in tool.

How much does Whisper Large cost in Factory Droid?

$0.00624 per minute of audio, per channel. Redaction: $0.0026 per minute. Entity detection: $0.00221 per minute. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Factory Droid plan is separate.

Do I need a Deepgram account to use Whisper Large in Factory Droid?

No. Spiral runs Whisper Large on its own Deepgram account. You sign in to Spiral once and never paste a key.

How long does it take to set up Whisper Large in Factory Droid?

About two minutes: add the server, then sign in, then check it.

Does Factory Droid wait while Whisper Large runs?

Whisper Large runs in the background. Factory Droid starts the run, checks on it and gives you the json when it's ready.

Which Whisper version is Whisper Large?

Whisper Large maps to OpenAI's large-v2 model. Evaluate its transcripts directly rather than assuming results from large-v3 benchmarks apply.

Can Whisper Large transcribe languages other than English?

Yes. Supported languages include French, German, Hindi, and Japanese, but accuracy varies by language. Set the spoken language deliberately for each recording.

How well does Whisper Large handle accents and background noise?

Whisper was trained for improved robustness to accents, background noise, and technical language. Still, check difficult passages against the recording before quoting them.

Can Whisper Large invent words?

Yes. Whisper can produce text that nobody spoke, so a fluent transcript is not proof of accuracy. Review quotations, names, and important numbers against the audio.

How should I handle misspelled product or company names?

Use find and replace for a known, repeatable spelling error. Check the correction in context before applying it throughout a transcript.

Get started

Start using Whisper Large in Factory Droid

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Factory Droid:

Set up Factory Droid

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options